EngineX/xc-llm-ascend
3
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

[MoE] [Refactor] Combine common_fused_moe and fused_moe (#3176)

Browse Source 
### What this PR does / why we need it?
1. Move additional functionalities from fused_moe.py to
common_fused_moe.py and remove fused_moe.py
2. Remove unnecessary custom classes from qwen3_moe.py, and it will be
completely removed after we release vllm-ascend v0.11.0

### Does this PR introduce _any_ user-facing change?
No

### How was this patch tested?

Qwen3-30B-A3B/Qwen3-30B-A3B-W8A8/DeepSeek-V3-W4A8-Pruing/deepseek-mtp/pangu-pro-moe-pruing:

1. Enable/Disable EP
3. Aclgraph & eager
4. SP


- vLLM version: v0.11.0

---------

Signed-off-by: Pr0Wh1teGivee <calvin_zhu0210@outlook.com>
Co-authored-by: weijinqian0 <12153182+weijinqian0@users.noreply.github.com>
This commit is contained in:
weichen
2025-10-09 14:12:46 +08:00
committed by GitHub
parent a36e3da78e
commit 94dd832815
17 changed files with 175 additions and 1110 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
vllm_ascend/ops/moe/token_dispatcher.py
View File

@@ -468,9 +468,6 @@ class TokenDispatcherWithAll2AllV(MoETokenDispatcher):
super().__init__(**kwargs)
self.with_quant = False
self.num_local_experts = kwargs.get("num_local_experts", 0)
self.num_global_redundant_experts = kwargs.get(
"num_global_redundant_experts", 0)
self.num_experts = self.num_experts + self.num_global_redundant_experts
self.hidden_shape = None
self.topk_weights = None